[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Signed-off-by: pallavi jaini <[email protected]>

comps/dataprep/pinecone/docker/docker-compose-dataprep-pinecone.yaml

@@ -39,4 +39,3 @@ services:
 networks:
   default:
     driver: bridge
-

comps/dataprep/pinecone/prepare_doc_pinecone.py

@@ -33,48 +33,47 @@
 tei_embedding_endpoint = os.getenv("TEI_EMBEDDING_ENDPOINT")
 upload_folder = "./uploaded_files/"
 
+
 def check_index_existance(client):
     print(f"[ check index existence ] checking {PINECONE_INDEX_NAME}")
-    
+
     existing_indexes = [index_info["name"] for index_info in pc.list_indexes()]
     if PINECONE_INDEX_NAME not in existing_indexes:
-        print(f"[ check index existence ] index does not exist")
+        print("[ check index existence ] index does not exist")
         return None
     else:
         return True
 
+
 def create_index(client):
     print(f"[ create index ] creating index {PINECONE_INDEX_NAME}")
     try:
         client.create_index(
-        name=PINECONE_INDEX_NAME,
-        dimension=768,
-        metric="cosine",
-        spec=ServerlessSpec(cloud="aws", region="us-east-1"),
+            name=PINECONE_INDEX_NAME,
+            dimension=768,
+            metric="cosine",
+            spec=ServerlessSpec(cloud="aws", region="us-east-1"),
         )
         print(f"[ create index ] index {PINECONE_INDEX_NAME} successfully created")
     except Exception as e:
         print(f"[ create index ] fail to create index {PINECONE_INDEX_NAME}: {e}")
         return False
     return True
 
+
 def store_by_id(client, key, value):
     print(f"[ store by id ] storing ids of {key}")
     try:
         index = client.Index(PINECONE_INDEX_NAME)
-        index.upsert(
-            vectors=[
-                {"id":"file:" + key, "values":value}
-            ], 
-            namespace="ns1"
-                )
-
+        index.upsert(vectors=[{"id": "file:" + key, "values": value}], namespace="ns1")
+
         print(f"[ store by id ] store document success. id: file:{key}")
     except Exception as e:
         print(f"[ store by id ] fail to store document file:{key}: {e}")
         return False
     return True
-
+
+
 def ingest_data_to_pinecone(doc_path: DocPath):
     """Ingest document to Pinecone."""
     path = doc_path.path
@@ -125,7 +124,7 @@ def ingest_data_to_pinecone(doc_path: DocPath):
             index_name=PINECONE_INDEX_NAME,
         )
         print(f"Processed batch {i//batch_size + 1}/{(num_chunks-1)//batch_size + 1}")
-    
+
     # store file_ids into index file-keys
     pc = Pinecone(api_key=PINECONE_API_KEY)
 

comps/dataprep/pinecone/requirements.txt

@@ -7,9 +7,9 @@ fastapi
 huggingface_hub
 langchain
 langchain-community
-langchain-text-splitters
-langchain-pinecone
 langchain-openai
+langchain-pinecone
+langchain-text-splitters
 langsmith
 markdown
 numpy
@@ -18,11 +18,11 @@ opentelemetry-exporter-otlp
 opentelemetry-sdk
 pandas
 Pillow
-prometheus-fastapi-instrumentator
 pinecone-client
+prometheus-fastapi-instrumentator
+pymupdf
 pyspark
 python-bidi==0.4.2
-pymupdf
 python-docx
 python-pptx
 sentence_transformers

comps/retrievers/langchain/pinecone/requirements.txt

@@ -14,9 +14,9 @@ opentelemetry-sdk
 pandas
 Pillow
 pinecone-client
+prometheus_fastapi_instrumentator
 pymupdf
 python-docx
 sentence_transformers
 shortuuid
-prometheus_fastapi_instrumentator
 uvicorn

comps/retrievers/langchain/pinecone/retriever_pinecone.py

@@ -4,10 +4,10 @@
 import os
 import time
 
+from config import EMBED_MODEL, PINECONE_API_KEY, PINECONE_INDEX_NAME
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceHubEmbeddings
 from langchain_pinecone import PineconeVectorStore
 from langsmith import traceable
-from config import EMBED_MODEL, PINECONE_API_KEY, PINECONE_INDEX_NAME
 from pinecone import Pinecone, ServerlessSpec
 
 from comps import (
@@ -36,19 +36,17 @@
 def retrieve(input: EmbedDoc) -> SearchedDoc:
     start = time.time()
 
-    pc = Pinecone(api_key=PINECONE_API_KEY) 
+    pc = Pinecone(api_key=PINECONE_API_KEY)
 
     index = pc.Index(PINECONE_INDEX_NAME)
-    print(index.describe_index_stats()['total_vector_count'])
+    print(index.describe_index_stats()["total_vector_count"])
     # check if the Pinecone index has data
-    if index.describe_index_stats()['total_vector_count'] == 0:
+    if index.describe_index_stats()["total_vector_count"] == 0:
         result = SearchedDoc(retrieved_docs=[], initial_query=input.text)
         statistics_dict["opea_service@retriever_pinecone"].append_latency(time.time() - start, None)
         return result
 
-    search_res = vector_db.max_marginal_relevance_search(
-        query=input.text, k=input.k, fetch_k=input.fetch_k
-    )
+    search_res = vector_db.max_marginal_relevance_search(query=input.text, k=input.k, fetch_k=input.fetch_k)
     # if the Pinecone index has data, perform the search
     if input.search_type == "similarity":
         docs_and_similarities = vector_db.similarity_search_by_vector_with_score(embedding=input.embedding, k=input.k)